INDEX
Explanations
references to presidential figures and their administrations
New Auto-Interp
Negative Logits
èIJ½
-0.16
Record
-0.15
ago
-0.15
preci
-0.14
å·
-0.14
ivan
-0.14
abal
-0.14
Ñģлов
-0.13
"default
-0.13
tar
-0.13
POSITIVE LOGITS
erece
0.16
zig
0.16
\/\/
0.15
zh
0.14
erview
0.14
ilight
0.14
Úĺ
0.14
franch
0.14
ofs
0.14
ofire
0.14
Activations Density 0.036%